© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50281
    Prev
    Next
    INDEX
    Explanations

    кон

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    லக
    -0.08
     inclusion
    -0.08
     EC
    -0.07
     Inclusion
    -0.07
     AC
    -0.07
     Array
    -0.07
     provisional
    -0.07
     VAR
    -0.07
     MEC
    -0.07
    (Array
    -0.07
    POSITIVE LOGITS
    Chr
    0.09
    Nhap
    0.09
     absentee
    0.08
    �
    0.08
    chr
    0.08
    score
    0.08
     chr
    0.08
    До
    0.08
    уси
    0.07
    brates
    0.07
    Activations Density 0.001%

    No Known Activations